SOURCE-LINKED INTELLIGENCE

Hidden relationships in a document-derived property graph: top-k chunk embeddings and inverse-distance weighting over a dynamically evolving ontology

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Large language models extracting knowledge graphs from text capture only explicitly stated facts, often leaving semantically related entities disconnected across documents. We present an additive, engine-neutral second pass that discovers these latent ties without altering extracted facts. Each document is chunked and embedded once; top-k nearest- neighbor queries across existing chunks yield candidate node pairs via entity membership maps. Candidate pairs are scored using Shepard inverse-distance weighting with a rescaled chord distance metric, avoiding the threshold-collapsing flaw of affine

Read original source ↗ Open in workspace

recordType

paper

region

Global